No abstract

Futures markets offer investors many attractive advantages, including high leverage, high liquidity, fair, and fast returns. Highly leveraged positions and big contract sizes, on the other hand, expose investors to the risk of massive losses from even minor market changes. Among the numerous stock market forecasting tools, deep learning has recently emerged as a favorite tool in the research community. This study presents an approach for applying deep learning models to predict the monthly average of the Taiwan Capitalization Weighted Stock Index (TAIEX) to support decision-making in trading Mini-TAIEX futures (MTX). We inspected many global financial and economic factors to find the most valuable predictor variables for the TAIEX, and we examined three different deep learning architectures for building prediction models. A simulation on trading MTX was then performed with a simple trading strategy and two different stop-loss strategies to show the effectiveness of the models. We found that the Temporal Convolutional Network (TCN) performed better than other models, including the two baselines, i.e., linear regression and extreme gradient boosting. Moreover, stop-loss strategies are necessary, and a simple one could be sufficient to reduce a severe loss effectively.

No abstract

While real-time bidding brings a huge profit for online businesses, it also becomes a potential target for malicious purposes. In real-time bidding, the bid request traffic could be classified into two kinds: intentional and non-intentional. Intentional bid requests come from ordinal web users while non-intentional bid requests come from abnormal web users. From the perspective of a demand-side platform (DSP), the budget of advertisers should be used as effectively as possible by limiting non-intentional traffic. Therefore, it is essential to classify and predict these two kinds of bid request traffic. In this research, we propose a real-time filtering bid requests (RFBR) model to predict whether an incoming bid request is intentional or non-intentional from the DSP’s viewpoint. Our model is built on three stages. In the first stage, we analyzed all potential attributes in the bid request scheme and figured out the relations between abnormal behaviors and their attributes; in the second stage, a classification model was built to classify normal and abnormal audiences by the extracted features and self-defined thresholds; in the third stage, a RFBR model was built to classify intentional and non-intentional bid requests. The experimental result shows that our system can effectively classify incoming bid requests.

No abstract